pi-hashline-edit-pro 4.3.1 → 4.3.2

package/README.md

@@ -162,7 +162,9 @@ Auto-read keeps the same 50KB and 2000-line budget as `read`. Auto-read and Diff
 
 Auto-read all is off by default and has three modes, selected in `/hashline-config`: `off` injects nothing, `on` discovers every file in the working directory that is not git-ignored (`git ls-files`, falling back to `ripgrep`, then to a directory walk), and `git` uses `git ls-files` only, injecting nothing when the working directory is not a git repository. On the first turn of a session, the extension discovers the files, reads each one, and attaches the resulting `anchor│content` rows to the conversation as one extension message before the model answers. Those anchors are served exactly like `read` output, so the model can `replace` and `insert` immediately without calling `read` first. The message is injected once per session; resumed, forked, and cloned sessions that already contain it skip the injection.
 
-Files are filtered before injection: symlinks, directories, image extensions, binary files (a NUL byte in the first 8KB), files over 200KB, and any file whose name is in the built-in skip list (currently `package-lock.json`, matched by file name anywhere in the tree) are skipped. The attachment stops at 500 files or at a byte budget derived from the model's context window (200KB floor, 2MB ceiling), and it never drops below one file. Skipped and not-attached files are named at the end of the message so the model can `read` them on demand. A file whose `read` output is truncated keeps its truncation hint, so the rest can be paged in with `read`.
+Files are filtered before injection: symlinks, directories, image extensions (including SVG), binary files (a NUL byte in the first 8KB), files over 200KB, any path with a vendored segment (vendor, node_modules, bower_components, third_party, thirdparty, jspm_packages, .venv, venv, site-packages, __pycache__, .tox, .gradle, .terraform, Pods, Carthage, DerivedData, coreui, coreui-icons, case-insensitive), and vendored or generated names and patterns (*.min.js, *.min.css, *.min.mjs, *-min.js, *-min.css, *.bundle.*, *.chunk.*, *.umd.js, *.map, *.lock, package-lock.json, yarn.lock, composer.lock, Gemfile.lock, Cargo.lock, poetry.lock, Pipfile.lock, go.sum, flake.lock, *.generated.*, *.gen.*, *_pb2.py, *.pb.go, *.g.dart, *.freezed.dart, *.designer.cs, *.g.cs, *.snap, .eslintcache, coreui-icons.*, coreui.css) are skipped. The attachment stops at 500 files or at a byte budget derived from the model context window (200KB floor, 2MB ceiling), and it never drops below one file. Skipped and not-attached files are named at the end of the message so the model can `read` them on demand. A file whose `read` output is truncated keeps its truncation hint, so the rest can be paged in with `read`.
+
+Each attached file carries a status line: `[complete, N lines; do NOT re-read]` means the section is fully attached and must be edited directly without calling `read`, while `[truncated, showing M of N lines; use read with offset=X to continue]` means only the first bytes are attached. A coverage line after the header reports complete versus truncated counts and the number of 48KB file-boundary chunks the payload splits into, so a host-side cut never tears a file in the middle.
 
 The setting lives in `/hashline-config` as Auto-read all and in `config.json` as `autoReadAll` (`"off"`, `"on"`, or `"git"`; older configs with `true` or `false` are read as `"on"` or `"off"`).
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-hashline-edit-pro",
-  "version": "4.3.1",
+  "version": "4.3.2",
   "type": "module",
   "description": "Hash-anchored read/replace/insert/grep tools for pi-coding-agent. Every line gets a unique 4-char tokenizer-friendly anchor that stays stable across edits; stale or ambiguous anchors are rejected, never fuzzy-matched. Undo persists across restarts.",
   "main": "index.ts",

package/src/auto-read-all.ts

@@ -22,9 +22,10 @@ const EXEC_MAX_BYTES = 64 * 1024 * 1024;
 const SCAN_CONCURRENCY = 32;
 const SCAN_LIMIT_MULTIPLIER = 4;
 const MAX_REPORTED_OMISSIONS = 50;
+export const AUTO_READ_ALL_CHUNK_BYTES = 48 * 1024;
 
 const HEADER =
-  "[hashline auto-read-all] The content of every non-ignored project file is attached below with live hashline anchors. Each anchor│content row is already owned and served for this session, so replace and insert can target those anchors directly without calling read first. Rows with a truncation hint are only partially shown; call read with the hinted offset to see the rest.";
+  "[hashline auto-read-all] The content of every non-ignored project file is attached below with live hashline anchors. Each anchor│content row is already owned and served for this session, so replace and insert can target those anchors directly without calling read first. Sections marked [complete] are fully attached; do NOT call read for them. Only sections marked [truncated] need read. Rows with a truncation hint are only partially shown; call read with the hinted offset to see the rest.";
 
 const IMAGE_EXTENSIONS = new Set([
   ".avif",
@@ -38,14 +39,71 @@ const IMAGE_EXTENSIONS = new Set([
   ".jxl",
   ".png",
   ".psd",
+  ".svg",
   ".tif",
   ".tiff",
   ".webp",
 ]);
 
-export const AUTO_READ_ALL_EXCLUDED_NAMES = ["package-lock.json"];
-
+export const AUTO_READ_ALL_EXCLUDED_SEGMENTS = [
+  "vendor",
+  "node_modules",
+  "bower_components",
+  "third_party",
+  "thirdparty",
+  "jspm_packages",
+  ".venv",
+  "venv",
+  "site-packages",
+  "__pycache__",
+  ".tox",
+  ".gradle",
+  ".terraform",
+  "pods",
+  "carthage",
+  "deriveddata",
+  "coreui",
+  "coreui-icons",
+];
+export const AUTO_READ_ALL_EXCLUDED_NAMES = [
+  "package-lock.json",
+  "yarn.lock",
+  "composer.lock",
+  "gemfile.lock",
+  "cargo.lock",
+  "poetry.lock",
+  "pipfile.lock",
+  "go.sum",
+  "flake.lock",
+  ".eslintcache",
+];
 const EXCLUDED_NAME_SET = new Set(AUTO_READ_ALL_EXCLUDED_NAMES);
+const EXCLUDED_SEGMENT_SET = new Set(AUTO_READ_ALL_EXCLUDED_SEGMENTS);
+function isExcludedBySegment(path: string): boolean {
+  for (const segment of path.split("/")) {
+    if (EXCLUDED_SEGMENT_SET.has(segment.toLowerCase())) return true;
+  }
+  return false;
+}
+function isExcludedByPattern(baseLower: string): boolean {
+  if (baseLower.endsWith(".min.js") || baseLower.endsWith(".min.css") || baseLower.endsWith(".min.mjs")) return true;
+  if (baseLower.endsWith("-min.js") || baseLower.endsWith("-min.css")) return true;
+  if (baseLower.includes(".bundle.") || baseLower.includes(".chunk.")) return true;
+  if (baseLower.endsWith(".umd.js")) return true;
+  if (baseLower.endsWith(".map")) return true;
+  if (baseLower.endsWith(".lock")) return true;
+  if (baseLower.includes(".generated.") || baseLower.includes(".gen.")) return true;
+  if (baseLower.endsWith("_pb2.py")) return true;
+  if (baseLower.endsWith(".pb.go")) return true;
+  if (baseLower.endsWith(".g.dart")) return true;
+  if (baseLower.endsWith(".freezed.dart")) return true;
+  if (baseLower.endsWith(".designer.cs")) return true;
+  if (baseLower.endsWith(".g.cs")) return true;
+  if (baseLower.endsWith(".snap")) return true;
+  if (baseLower.startsWith("coreui-icons.")) return true;
+  if (baseLower === "coreui.css") return true;
+  return false;
+}
 
 const WALK_IGNORED_DIRS = new Set([
   ".git",
@@ -79,11 +137,22 @@ export interface AutoReadAllDiscovery {
   skippedByName: number;
 }
 
+export interface AutoReadAllSection {
+  file: string;
+  text: string;
+  complete: boolean;
+  totalLines: number;
+  shownLines: number;
+  nextOffset?: number;
+}
 export interface AutoReadAllInjection {
   text: string;
   files: number;
   bytes: number;
   omitted: string[];
+  chunks: string[];
+  completeFiles: number;
+  truncatedFiles: number;
 }
 
 function runCommand(command: string, args: string[], cwd: string): Promise<{ stdout: string; code: number }> {
@@ -129,7 +198,7 @@ async function walkDir(dir: string, base: string, out: string[]): Promise<void>
     if (entry.isSymbolicLink()) continue;
     const full = join(dir, entry.name);
     if (entry.isDirectory()) {
-      if (WALK_IGNORED_DIRS.has(entry.name)) continue;
+      if (WALK_IGNORED_DIRS.has(entry.name) || EXCLUDED_SEGMENT_SET.has(entry.name.toLowerCase())) continue;
       await walkDir(full, base, out);
     } else if (entry.isFile()) {
       out.push(toPosix(relative(base, full)));
@@ -202,7 +271,8 @@ export async function discoverAutoReadAllFiles(cwd: string, mode: AutoReadAllMod
   const includable: string[] = [];
   let skippedByName = 0;
   for (const file of unique) {
-    if (EXCLUDED_NAME_SET.has(baseNameOf(file).toLowerCase())) skippedByName += 1;
+    const baseLower = baseNameOf(file).toLowerCase();
+    if (EXCLUDED_NAME_SET.has(baseLower) || isExcludedBySegment(file) || isExcludedByPattern(baseLower)) skippedByName += 1;
     else includable.push(file);
   }
   const scanWindow = includable.slice(0, AUTO_READ_ALL_MAX_FILES * SCAN_LIMIT_MULTIPLIER);
@@ -247,12 +317,34 @@ export async function discoverAutoReadAllFiles(cwd: string, mode: AutoReadAllMod
   return { files, source, discovered: unique.length, skippedBinary, skippedLarge, skippedOther, skippedByName };
 }
 
-async function renderFile(file: string, cwd: string): Promise<string | undefined> {
+export function chunkAutoReadAllSections(sections: string[], maxBytes: number = AUTO_READ_ALL_CHUNK_BYTES): string[] {
+  const chunks: string[] = [];
+  let current: string[] = [];
+  let currentBytes = 0;
+  for (const section of sections) {
+    const sectionBytes = Buffer.byteLength(section, "utf-8") + 2;
+    if (current.length > 0 && currentBytes + sectionBytes > maxBytes) {
+      chunks.push(current.join("\n\n"));
+      current = [];
+      currentBytes = 0;
+    }
+    current.push(section);
+    currentBytes += sectionBytes;
+  }
+  if (current.length > 0) chunks.push(current.join("\n\n"));
+  return chunks;
+}
+async function renderFile(file: string, cwd: string): Promise<AutoReadAllSection | undefined> {
   try {
     const { normalized, fileHashes, absolutePath } = await readNormFile(file, cwd, { maxLines: MAX_HASH_LINES });
     const preview = await fmtReadPreview(normalized, {}, fileHashes, absolutePath, DEFAULT_MAX_BYTES, DEFAULT_MAX_LINES);
     serveRows(absolutePath, fileHashes, splitLines(normalized), preview.servedHashes);
-    return `=== ${file} ===\n${preview.text}`;
+    const totalLines = fileHashes.length;
+    const shownLines = preview.servedHashes.length;
+    const complete = preview.truncation === undefined && preview.nextOffset === undefined && shownLines >= totalLines;
+    const status = complete ? `[complete, ${totalLines} lines; do NOT re-read]` : `[truncated, showing ${shownLines} of ${totalLines} lines; use read with offset=${preview.nextOffset ?? shownLines + 1} to continue]`;
+    const nextOffset = preview.nextOffset;
+    return { file, text: `=== ${file} ===\n${status}\n${preview.text}`, complete, totalLines, shownLines, ...(nextOffset !== undefined ? { nextOffset } : {}) };
   } catch (error) {
     console.error(`Auto-read all: skipped ${file}:`, error);
     return undefined;
@@ -269,7 +361,7 @@ function buildFooter(attached: number, discovery: AutoReadAllDiscovery, omitted:
   if (discovery.skippedBinary > 0) notes.push(`${discovery.skippedBinary} binary or image file(s) skipped`);
   if (discovery.skippedLarge > 0) notes.push(`${discovery.skippedLarge} file(s) over ${formatSize(AUTO_READ_ALL_MAX_FILE_BYTES)} skipped`);
   if (discovery.skippedOther > 0) notes.push(`${discovery.skippedOther} unreadable path(s) skipped`);
-  if (discovery.skippedByName > 0) notes.push(`${discovery.skippedByName} file(s) skipped by name (${AUTO_READ_ALL_EXCLUDED_NAMES.join(", ")})`);
+  if (discovery.skippedByName > 0) notes.push(`${discovery.skippedByName} file(s) skipped by vendor/name/pattern rules`);
   const listed = omitted.slice(0, MAX_REPORTED_OMISSIONS).join(", ");
   const more = omitted.length > MAX_REPORTED_OMISSIONS ? `, ... (+${omitted.length - MAX_REPORTED_OMISSIONS} more)` : "";
   const omissionNote = omitted.length > 0 ? ` Not attached: ${listed}${more}. Use read for those.` : "";
@@ -280,26 +372,33 @@ function buildFooter(attached: number, discovery: AutoReadAllDiscovery, omitted:
 export async function buildAutoReadAllInjection(cwd: string, budgetBytes: number, mode: AutoReadAllMode = "on"): Promise<AutoReadAllInjection | undefined> {
   const discovery = await discoverAutoReadAllFiles(cwd, mode);
   if (discovery.files.length === 0) return undefined;
-  const sections: string[] = [];
+  const sections: AutoReadAllSection[] = [];
   const omitted: string[] = [];
   let bytes = 0;
+  let completeFiles = 0;
+  let truncatedFiles = 0;
   for (const file of discovery.files) {
     const section = await renderFile(file, cwd);
     if (section === undefined) {
       omitted.push(file);
       continue;
     }
-    const sectionBytes = Buffer.byteLength(section, "utf-8") + 1;
+    const sectionBytes = Buffer.byteLength(section.text, "utf-8") + 1;
     if (sections.length > 0 && bytes + sectionBytes > budgetBytes) {
       omitted.push(file);
       continue;
     }
     sections.push(section);
     bytes += sectionBytes;
+    if (section.complete) completeFiles += 1;
+    else truncatedFiles += 1;
   }
   if (sections.length === 0) return undefined;
-  const text = `${HEADER}\n\n${sections.join("\n\n")}\n\n${buildFooter(sections.length, discovery, omitted)}`;
-  return { text, files: sections.length, bytes, omitted };
+  const sectionTexts = sections.map((section) => section.text);
+  const chunks = chunkAutoReadAllSections(sectionTexts);
+  const coverage = `[coverage: ${completeFiles} complete, ${truncatedFiles} truncated, ${chunks.length} chunk(s) x 48KB with file boundaries preserved; do NOT re-read complete files]`;
+  const text = `${HEADER}\n\n${coverage}\n\n${sectionTexts.join("\n\n")}\n\n${buildFooter(sections.length, discovery, omitted)}`;
+  return { text, files: sections.length, bytes, omitted, chunks, completeFiles, truncatedFiles };
 }
 
 export function autoReadAllBudget(model: { contextWindow?: number } | undefined): number {